# Libraries for data manipulation
import  pandas as pd
import numpy as np

# Libraries for visualization
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objects as go
from plotly.subplots import make_subplots

# Load the Coffee Dataset
df = pd.read_csv(r"C:\Users\nanav\Downloads\Coffee Dataset.csv")

df.head(10)

# Shape of the dataframe
df.shape

(4042, 111)

# Name of each column in dataframe
df.columns.tolist()

['Submission ID',
 'What is your age?',
 'How many cups of coffee do you typically drink per day?',
 'Where do you typically drink coffee?',
 'Where do you typically drink coffee? (At home)',
 'Where do you typically drink coffee? (At the office)',
 'Where do you typically drink coffee? (On the go)',
 'Where do you typically drink coffee? (At a cafe)',
 'Where do you typically drink coffee? (None of these)',
 'How do you brew coffee at home?',
 'How do you brew coffee at home? (Pour over)',
 'How do you brew coffee at home? (French press)',
 'How do you brew coffee at home? (Espresso)',
 'How do you brew coffee at home? (Coffee brewing machine (e.g. Mr. Coffee))',
 'How do you brew coffee at home? (Pod/capsule machine (e.g. Keurig/Nespresso))',
 'How do you brew coffee at home? (Instant coffee)',
 'How do you brew coffee at home? (Bean-to-cup machine)',
 'How do you brew coffee at home? (Cold brew)',
 'How do you brew coffee at home? (Coffee extract (e.g. Cometeer))',
 'How do you brew coffee at home? (Other)',
 'How else do you brew coffee at home?',
 'On the go, where do you typically purchase coffee?',
 'On the go, where do you typically purchase coffee? (National chain (e.g. Starbucks, Dunkin))',
 'On the go, where do you typically purchase coffee? (Local cafe)',
 'On the go, where do you typically purchase coffee? (Drive-thru)',
 'On the go, where do you typically purchase coffee? (Specialty coffee shop)',
 'On the go, where do you typically purchase coffee? (Deli or supermarket)',
 'On the go, where do you typically purchase coffee? (Other)',
 'Where else do you purchase coffee?',
 'What is your favorite coffee drink?',
 'Please specify what your favorite coffee drink is',
 'Do you usually add anything to your coffee?',
 'Do you usually add anything to your coffee? (No - just black)',
 'Do you usually add anything to your coffee? (Milk, dairy alternative, or coffee creamer)',
 'Do you usually add anything to your coffee? (Sugar or sweetener)',
 'Do you usually add anything to your coffee? (Flavor syrup)',
 'Do you usually add anything to your coffee? (Other)',
 'What else do you add to your coffee?',
 'What kind of dairy do you add?',
 'What kind of dairy do you add? (Whole milk)',
 'What kind of dairy do you add? (Skim milk)',
 'What kind of dairy do you add? (Half and half)',
 'What kind of dairy do you add? (Coffee creamer)',
 'What kind of dairy do you add? (Flavored coffee creamer)',
 'What kind of dairy do you add? (Oat milk)',
 'What kind of dairy do you add? (Almond milk)',
 'What kind of dairy do you add? (Soy milk)',
 'What kind of dairy do you add? (Other)',
 'What kind of sugar or sweetener do you add?',
 'What kind of sugar or sweetener do you add? (Granulated Sugar)',
 'What kind of sugar or sweetener do you add? (Artificial Sweeteners (e.g., Splenda))',
 'What kind of sugar or sweetener do you add? (Honey)',
 'What kind of sugar or sweetener do you add? (Maple Syrup)',
 'What kind of sugar or sweetener do you add? (Stevia)',
 'What kind of sugar or sweetener do you add? (Agave Nectar)',
 'What kind of sugar or sweetener do you add? (Brown Sugar)',
 'What kind of sugar or sweetener do you add? (Raw Sugar (Turbinado))',
 'What kind of flavorings do you add?',
 'What kind of flavorings do you add? (Vanilla Syrup)',
 'What kind of flavorings do you add? (Caramel Syrup)',
 'What kind of flavorings do you add? (Hazelnut Syrup)',
 'What kind of flavorings do you add? (Cinnamon (Ground or Stick))',
 'What kind of flavorings do you add? (Peppermint Syrup)',
 'What kind of flavorings do you add? (Other)',
 'What other flavoring do you use?',
 "Before today's tasting, which of the following best described what kind of coffee you like?",
 'How strong do you like your coffee?',
 'What roast level of coffee do you prefer?',
 'How much caffeine do you like in your coffee?',
 'Lastly, how would you rate your own coffee expertise?',
 'Coffee A - Bitterness',
 'Coffee A - Acidity',
 'Coffee A - Personal Preference',
 'Coffee A - Notes',
 'Coffee B - Bitterness',
 'Coffee B - Acidity',
 'Coffee B - Personal Preference',
 'Coffee B - Notes',
 'Coffee C - Bitterness',
 'Coffee C - Acidity',
 'Coffee C - Personal Preference',
 'Coffee C - Notes',
 'Coffee D - Bitterness',
 'Coffee D - Acidity',
 'Coffee D - Personal Preference',
 'Coffee D - Notes',
 'Between Coffee A, Coffee B, and Coffee C which did you prefer?',
 'Between Coffee A and Coffee D, which did you prefer?',
 'Lastly, what was your favorite overall coffee?',
 'Do you work from home or in person?',
 'In total, much money do you typically spend on coffee in a month?',
 'Why do you drink coffee?',
 'Why do you drink coffee? (It tastes good)',
 'Why do you drink coffee? (I need the caffeine)',
 'Why do you drink coffee? (I need the ritual)',
 'Why do you drink coffee? (It makes me go to the bathroom)',
 'Why do you drink coffee? (Other)',
 'Other reason for drinking coffee',
 'Do you like the taste of coffee?',
 'Do you know where your coffee comes from?',
 "What is the most you've ever paid for a cup of coffee?",
 "What is the most you'd ever be willing to pay for a cup of coffee?",
 'Do you feel like you’re getting good value for your money when you buy coffee at a cafe?',
 'Approximately how much have you spent on coffee equipment in the past 5 years?',
 'Do you feel like you’re getting good value for your money with regards to your coffee equipment?',
 'Gender',
 'Education Level',
 'Ethnicity/Race',
 'Employment Status',
 'Number of Children',
 'Political Affiliation']

# Datatype of each column in dataframe
df.dtypes

Submission ID                                              object
What is your age?                                          object
How many cups of coffee do you typically drink per day?    object
Where do you typically drink coffee?                       object
Where do you typically drink coffee? (At home)             object
                                                            ...  
Education Level                                            object
Ethnicity/Race                                             object
Employment Status                                          object
Number of Children                                         object
Political Affiliation                                      object
Length: 111, dtype: object

df.isnull().any()

Submission ID                                              False
What is your age?                                           True
How many cups of coffee do you typically drink per day?     True
Where do you typically drink coffee?                        True
Where do you typically drink coffee? (At home)              True
                                                           ...  
Education Level                                             True
Ethnicity/Race                                              True
Employment Status                                           True
Number of Children                                          True
Political Affiliation                                       True
Length: 111, dtype: bool

df.describe()

# Dropping columns with more than 70% NaN values
threshold = len(df) * 0.7
df.dropna(thresh=threshold, axis=1)

# Step 2: Drop rows with too many NaN values (more than 50%)
df = df.dropna(thresh=df.shape[1] * 0.5, axis=0)

# Step 4: Remove any duplicate rows
df.drop_duplicates()

# Sample renaming of specific columns
df.rename(columns ={
    'How do you brew coffee at home? (Pour over)':'PourOver',
    'How do you brew coffee at home? (French press)':'FrenchPress',
    'How do you brew coffee at home? (Espresso)':'Espresso',
    'How do you brew coffee at home? (Coffee brewing machine (e.g. Mr. Coffee))':'CoffeeBrewingMachine',
    'How do you brew coffee at home? (Pod/capsule machine (e.g. Keurig/Nespresso))':'CapsuleMachine',
    'How do you brew coffee at home? (Instant coffee)':'InstantCoffee',
    'How do you brew coffee at home? (Bean-to-cup machine)':'BeanToCupMachine',
    'How do you brew coffee at home? (Cold brew)':'ColdBrew',
    'How do you brew coffee at home? (Coffee extract (e.g. Cometeer))':'CoffeeExtract',
    'How do you brew coffee at home? (Other)':'OtherMachine'},inplace =True)

# Sample renaming of specific columns
df.rename(columns ={'On the go, where do you typically purchase coffee? (National chain (e.g. Starbucks, Dunkin))':'NationalCahin',
 'On the go, where do you typically purchase coffee? (Local cafe)':'LocalCafe',
 'On the go, where do you typically purchase coffee? (Drive-thru)':'DeiveThru',
 'On the go, where do you typically purchase coffee? (Specialty coffee shop)':'SpecialtyCoffeeShop',
 'On the go, where do you typically purchase coffee? (Deli or supermarket)':'SuperMarket',
 'On the go, where do you typically purchase coffee? (Other)':'OtherLocation'},inplace =True)

# Sample renaming of specific columns
df.rename(columns ={
 'Where do you typically drink coffee? (At home)':'AtHome',
 'Where do you typically drink coffee? (At the office)':'AtOffice',
 'Where do you typically drink coffee? (On the go)':'OnTheGo',
 'Where do you typically drink coffee? (At a cafe)':'AtCafe',
 'Where do you typically drink coffee? (None of these)':'NoneOfThese'},inplace =True)

# Sample renaming of specific columns
df.rename(columns ={
 'What kind of sugar or sweetener do you add? (Artificial Sweeteners (e.g., Splenda))':'Artificial Sweeteners',
 'What kind of sugar or sweetener do you add? (Granulated Sugar)':'GranulatedSugar',
 'What kind of sugar or sweetener do you add? (Honey)':'Honey',
 'What kind of sugar or sweetener do you add? (Maple Syrup)':'MapleSyrup',
 'What kind of sugar or sweetener do you add? (Stevia)':'Stevia',
 'What kind of sugar or sweetener do you add? (Agave Nectar)':'AgaveNectar',
 'What kind of sugar or sweetener do you add? (Brown Sugar)':'BrownSugar',
 'What kind of sugar or sweetener do you add? (Raw Sugar (Turbinado))':'RawSugar'},inplace =True)

# Sample renaming of specific columns
df.rename(columns ={'What kind of dairy do you add? (Whole milk)':'WholeMilk',
 'What kind of dairy do you add? (Skim milk)':'SkimMilk',
 'What kind of dairy do you add? (Half and half)':'HalfAndHalf',
 'What kind of dairy do you add? (Coffee creamer)':'CoffeeCreamer',
 'What kind of dairy do you add? (Flavored coffee creamer)':'FalavoredCoffeeCreamer',
 'What kind of dairy do you add? (Oat milk)':'OatMilk',
 'What kind of dairy do you add? (Almond milk)':'AlmondMilk',
 'What kind of dairy do you add? (Soy milk)':'SoyMilk',
 'What kind of dairy do you add? (Other)':'OtherMilk'},inplace =True)

brewing_columns = [
 'PourOver',
 'FrenchPress',
 'Espresso',
 'CoffeeBrewingMachine',
 'CapsuleMachine',
 'InstantCoffee',
 'BeanToCupMachine',
 'ColdBrew',
 'CoffeeExtract',
 'OtherMachine',
   
]
# Convert all brewing method columns to boolean (True for non-zero/non-empty, False for NaN or 0)
df[brewing_columns] = df[brewing_columns].notna() & df[brewing_columns].astype(bool)

# Create the main column with the names of the brewing methods used
df['How do you brew coffee at home?'] = df[brewing_columns].apply(
    lambda row: ', '.join([col for col, val in row.items() if val]), axis=1
)

location =[
 'AtHome',
 'AtOffice',
 'OnTheGo',
 'AtCafe',
 'NoneOfThese']

# Convert all brewing method columns to boolean (True for non-zero/non-empty, False for NaN or 0)
df[location] = df[location].notna() & df[location].astype(bool)

# Create the main column with the names of the brewing methods used
df['Where do you typically drink coffee?'] = df[location].apply(
    lambda row: ', '.join([col for col, val in row.items() if val]), axis=1
)

buylocation =[
'NationalCahin',
'LocalCafe',
'DeiveThru',
'SpecialtyCoffeeShop',
'SuperMarket',
'OtherLocation']

# Convert all brewing method columns to boolean (True for non-zero/non-empty, False for NaN or 0)
df[buylocation] = df[buylocation].notna() & df[buylocation].astype(bool)
 
# Create the main column with the names of the brewing methods used
df['On the go, where do you typically purchase coffee?'] = df[buylocation].apply(
    lambda row: ', '.join([col for col, val in row.items() if val]), axis=1)

#Replacing categorical values into numerical values
df['What is your age?'] = df['What is your age?'].str.replace('years old','')

# Replace 'NULL' values with 'Unknown'
df['What is your age?']==df['What is your age?'].replace('NULL', '')
df['What is your age?']==df['What is your age?'].replace('years old', ' ')
df['What is your age?'] = df['What is your age?'].str.replace('years old','')

colors = ['goldenrod', 'lightblue', 'thistle', 'olivedrab', 'coral', 'mediumseagreen', 'slateblue']

# Count the occurrences using Seaborn's countplot
plt.figure(figsize=(8, 4))
ax = sns.countplot(data=df, x='What is your age?',hue='What is your age?',palette = colors)

# Adding bar labels on top of the bars
for bars in ax.containers:
    ax.bar_label(bars)

plt.title("Age Group Distribution")
plt.xlabel("Age Group")
plt.ylabel("Frequency")
plt.show()

# Create a horizontal bar chart
plt.figure(figsize=(10, 5))
ax = sns.countplot(y='Gender', data=df, hue='Gender', palette='viridis')

# Add bar labels
for bars in ax.containers:
    ax.bar_label(bars)

# Display the plot
plt.show()

gender_counts = df[df['Gender'].isin(['Male', 'Female'])]['Gender'].value_counts()

# Plotting the pie chart
plt.figure(figsize=(4, 4))
plt.pie(gender_counts, labels=gender_counts.index, autopct='%1.1f%%', startangle=140, colors=["SkyBlue", "Coral"])
plt.title("Gender Distribution in Dataset")
plt.show()

# Total Amount spend by gender 
df.groupby('Gender')['AveragePrice'].sum()

Gender
Female                7180.5
Male                 23529.0
Non-binary            1047.0
Other                   85.0
Prefer not to say      281.5
Name: AveragePrice, dtype: float64

# Define colors for the plot
colors = ["SkyBlue", "Coral", "Goldenrod", "SeaGreen", "SlateGray"]

# Filter to include only rows where "Where do you typically drink coffee?" is not NaN
coffee_consumers_df = df[df['Where do you typically drink coffee?'].notna()]
# Plot count of coffee consumers by Employment Status and Gender
plt.figure(figsize=(14, 4))
ax = sns.countplot(data=coffee_consumers_df, x='Employment Status', hue='Gender', palette=colors)
# Adding labels on top of each bar
for bars in ax.containers:
    ax.bar_label(bars)
# Display the plot
plt.title("Employment Status of Coffee Consumers by Gender")
plt.xlabel("Employment Status")
plt.ylabel("Count of Coffee Consumers")
plt.show()

# get the average price by removing unwanted characters '$' and by dividing lower_bound and upper_bound by '/2'
def parse_price(value):
    if pd.isnull(value):
        return None
    elif '-' in value:  # If the value is a range like "$4-$6"
        low, high = value.split('-')
        return (float(low.replace('$', '').strip()) + float(high.replace('$', '').strip())) / 2
    elif "More than" in value:  # If the value is "More than 20"
        return 20.0  # or choose a higher value like 25
    else:
        try:
            return float(value.replace('$', '').strip())  # Handle single values without ranges
        except ValueError:
            return None  # Default to None if there's an unexpected format

df["AveragePrice"] = df["What is the most you've ever paid for a cup of coffee?"].apply(parse_price)

# Creating subplots of histograms of showing various categories
fig = make_subplots(
    rows=4, cols=2,
    subplot_titles=("Gender", "What is your age?", "Education Level", "Ethnicity/Race",
                    "Employment Status", "Number of Children", "Political Affiliation", "AveragePrice")
)

# Add histograms for each subplot
fig.add_trace(go.Histogram(x=df['Gender']), row=1, col=1)
fig.add_trace(go.Histogram(x=df['What is your age?']), row=1, col=2)
fig.add_trace(go.Histogram(x=df['Education Level']), row=2, col=1)
fig.add_trace(go.Histogram(x=df['Ethnicity/Race']), row=2, col=2)
fig.add_trace(go.Histogram(x=df['Employment Status']), row=3, col=1)
fig.add_trace(go.Histogram(x=df['Number of Children']), row=3, col=2)
fig.add_trace(go.Histogram(x=df['Political Affiliation']), row=4, col=1)
fig.add_trace(go.Histogram(x=df['AveragePrice']), row=4, col=2)

# Update layout if needed
fig.update_layout(height=1200, width=1000, title_text="Count Plots")
fig.update_layout(showlegend=False)  # Hide the legend if not needed

# Show the figure
fig.show()

#Split the "On the go, where do you typically purchase coffee?" column and explode it

#Split the "On the go, where do you typically purchase coffee?" column and explode it
df_expanded = df.assign(
    Purchase_Location=df['On the go, where do you typically purchase coffee?'].str.split(', ')
).explode('Purchase_Location')

#Replace values in the Gender column
df_expanded['Gender'] = df_expanded['Gender'].str.replace('Other', 'Unknown')

#Remove empty entries after exploding
df_expanded = df_expanded[df_expanded['Purchase_Location'] != ""]

#Count occurrences of each location by gender
location_gender_counts = df_expanded.groupby(['Purchase_Location', 'Gender']).size().unstack(fill_value=0)

#Plotting the stacked bar chart
location_gender_counts.plot(kind="bar", stacked=True, figsize=(10, 5), color=['ivory', 'tan', 'olivedrab', 'lightblue'])
plt.title("On-the-Go Coffee Purchase Locations by Gender")
plt.xlabel("Purchase Location")
plt.ylabel("Count of Responses")
plt.legend(title="Gender", bbox_to_anchor=(1.05, 1), loc='upper left')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Plotting a pie chart to show the proportion of spending categories
# Grouping the data into spending categories for visualization
spending_categories = df['Approximately how much have you spent on coffee equipment in the past 5 years?'].value_counts(dropna=False)

# Plotting the pie chart
plt.figure(figsize=(6, 6))
plt.pie(spending_categories, labels=spending_categories.index, autopct='%1.1f%%', startangle=140, colors=plt.cm.Paired.colors)
plt.title("Proportion of Spending on Coffee Equipment Over 5 Years")
plt.show()

# Define the columns for which you want to plot value counts
columns = ['How do you brew coffee at home?', 'What kind of dairy do you add?', 'What kind of sugar or sweetener do you add?', 'What is your favorite coffee drink?']

# Set up a 2x2 grid for subplots
fig, axes = plt.subplots(2, 2, figsize=(14, 10))  # 2 rows, 2 columns
axes = axes.flatten()  # Flatten to easily access each subplot

# Loop through each column, split, explode, and create bar charts
for i, column in enumerate(columns):
    #Split the comma-separated values and explode, then drop null or empty values
    df_expanded = df[column].str.split(', ').explode().dropna()
    df_expanded = df_expanded[df_expanded != '']  # Remove empty strings
    
    #Get the top 3 most common values
    top_3_values = df_expanded.value_counts().nlargest(3)
    
    #Plot the bar chart for the top 3 values
    ax = axes[i]
    ax.bar(top_3_values.index, top_3_values.values,color=['indigo', 'khaki', 'lavender'])  # Create vertical bar chart
    ax.set_title(f'Top 3 Most Frequent {column}')
    ax.set_xlabel(column)
    ax.set_ylabel('Count')
    ax.tick_params(axis='x', rotation=45)  # Rotate x-axis labels for readability

# Adjust layout and spacing
plt.tight_layout(pad=3.0)  # Add padding to reduce overlap between subplots
plt.show()

	What kind of flavorings do you add?	What kind of flavorings do you add? (Vanilla Syrup)	What kind of flavorings do you add? (Caramel Syrup)	What kind of flavorings do you add? (Hazelnut Syrup)	What kind of flavorings do you add? (Cinnamon (Ground or Stick))	What kind of flavorings do you add? (Peppermint Syrup)	What kind of flavorings do you add? (Other)	What other flavoring do you use?	Lastly, how would you rate your own coffee expertise?	Coffee A - Bitterness	...	Coffee A - Personal Preference	Coffee B - Bitterness	Coffee B - Acidity	Coffee B - Personal Preference	Coffee C - Bitterness	Coffee C - Acidity	Coffee C - Personal Preference	Coffee D - Bitterness	Coffee D - Acidity	Coffee D - Personal Preference
count	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3938.000000	3798.000000	...	3789.000000	3780.000000	3767.000000	3773.000000	3764.000000	3751.000000	3766.000000	3767.000000	3765.000000	3764.000000
mean	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	5.693499	2.141127	...	3.310900	3.013228	2.223786	3.068646	3.071998	2.366836	3.064790	2.162729	3.858167	3.375930
std	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	1.948867	0.947163	...	1.185953	0.992875	0.865389	1.113546	0.999267	0.921048	1.128431	1.081546	1.007973	1.452504
min	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	1.000000	1.000000	...	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
25%	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	5.000000	1.000000	...	2.000000	2.000000	2.000000	2.000000	2.000000	2.000000	2.000000	1.000000	3.000000	2.000000
50%	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	6.000000	2.000000	...	3.000000	3.000000	2.000000	3.000000	3.000000	2.000000	3.000000	2.000000	4.000000	4.000000
75%	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	7.000000	3.000000	...	4.000000	4.000000	3.000000	4.000000	4.000000	3.000000	4.000000	3.000000	5.000000	5.000000
max	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	10.000000	5.000000	...	5.000000	5.000000	5.000000	5.000000	5.000000	5.000000	5.000000	5.000000	5.000000	5.000000

Exploratory Data Analysis¶

Data Overview¶

Here, we'll first look at the Coffee dataset. We'll check the first and last few rows to understand what the data looks like.¶

Basic Dataset information¶

Data Cleaning¶

Renaming Column Headers¶

Merging Sub-Columns¶

visualization Data Insights¶

Final Insights¶

After analyzing the data, we have gathered key insights about customer coffee spending patterns based on age, gender, education status,ethincity race.¶

Actionable Insights¶

Recomendations¶

	Submission ID	What is your age?	How many cups of coffee do you typically drink per day?	Where do you typically drink coffee?	Where do you typically drink coffee? (At home)	Where do you typically drink coffee? (At the office)	Where do you typically drink coffee? (On the go)	Where do you typically drink coffee? (At a cafe)	Where do you typically drink coffee? (None of these)	How do you brew coffee at home?	...	What is the most you'd ever be willing to pay for a cup of coffee?	Do you feel like you’re getting good value for your money when you buy coffee at a cafe?	Approximately how much have you spent on coffee equipment in the past 5 years?	Do you feel like you’re getting good value for your money with regards to your coffee equipment?	Gender	Education Level	Ethnicity/Race	Employment Status	Number of Children	Political Affiliation
0	gMR29l	18-24 years old	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	BkPN0e	25-34 years old	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Pod/capsule machine (e.g. Keurig/Nespresso)	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	W5G8jj	25-34 years old	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Bean-to-cup machine	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	4xWgGr	35-44 years old	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Coffee brewing machine (e.g. Mr. Coffee)	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	QD27Q8	25-34 years old	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Pour over	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
5	V0LPeM	55-64 years old	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Pod/capsule machine (e.g. Keurig/Nespresso), E...	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
6	V0Gaxg	18-24 years old	NaN	At a cafe, At the office, At home, On the go	True	True	True	True	False	Pour over, French press, Espresso, Instant cof...	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
7	AdzRL0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
8	LbWda2	25-34 years old	Less than 1	At a cafe	False	False	False	True	False	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
9	EXQLWN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	Submission ID	What is your age?	How many cups of coffee do you typically drink per day?	Where do you typically drink coffee?	Where do you typically drink coffee? (At home)	Where do you typically drink coffee? (At the office)	Where do you typically drink coffee? (On the go)	Where do you typically drink coffee? (At a cafe)	Where do you typically drink coffee? (None of these)	How do you brew coffee at home?	...	What is the most you'd ever be willing to pay for a cup of coffee?	Do you feel like you’re getting good value for your money when you buy coffee at a cafe?	Approximately how much have you spent on coffee equipment in the past 5 years?	Do you feel like you’re getting good value for your money with regards to your coffee equipment?	Gender	Education Level	Ethnicity/Race	Employment Status	Number of Children	Political Affiliation
15	Zd694B	<18 years old	3	At home, At the office, At a cafe	True	True	False	True	False	Pour over, Espresso, Instant coffee	...	NaN	NaN	NaN	NaN	Other	Bachelor's degree	Other	Employed full-time	More than 3	Democrat
17	QA5JYA	25-34 years old	1	At home, At the office, On the go	True	True	True	False	False	Pour over, Coffee brewing machine (e.g. Mr. Co...	...	NaN	NaN	NaN	NaN	Female	Bachelor's degree	White/Caucasian	Employed full-time	NaN	Democrat
34	ylqbBg	45-54 years old	2	At home, At the office, At a cafe, On the go	True	True	True	True	False	Pour over, French press, Espresso	...	$8-$10	No	$500-$1000	Yes	Male	Master's degree	Other	Employed full-time	2	No affiliation
39	BGboZR	18-24 years old	3	At home, At a cafe, On the go	True	False	True	True	False	Pour over, French press, Espresso, Other, Cold...	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
41	YZzBdN	25-34 years old	2	At home, At the office	True	True	False	False	False	Pour over, Espresso	...	More than $20	Yes	$50-$100	Yes	Male	Master's degree	Asian/Pacific Islander	Unemployed	NaN	Independent
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4037	PA44VP	>65 years old	2	At home	True	False	False	False	False	Coffee brewing machine (e.g. Mr. Coffee)	...	$4-$6	No	Less than $20	Yes	Female	Master's degree	White/Caucasian	Retired	2	Democrat
4038	vNgpPD	>65 years old	2	At home	True	False	False	False	False	Coffee brewing machine (e.g. Mr. Coffee)	...	$2-$4	No	Less than $20	Yes	Male	Bachelor's degree	White/Caucasian	Retired	2	Republican
4039	g5ggRM	18-24 years old	1	At a cafe, At home, On the go, At the office	True	True	True	True	False	Espresso, Pod/capsule machine (e.g. Keurig/Nes...	...	More than $20	Yes	$300-$500	Yes	Male	Some college or associate's degree	White/Caucasian	Employed full-time	NaN	Democrat
4040	rlgbDN	25-34 years old	2	At home	True	False	False	False	False	Pour over	...	$8-$10	Yes	$100-$300	Yes	Male	Bachelor's degree	White/Caucasian	Unemployed	NaN	Democrat
4041	0EGYe9	25-34 years old	1	At home	True	False	False	False	False	Pour over, French press, Espresso, Other	...	$15-$20	Yes	$500-$1000	Yes	Female	Doctorate or professional degree	White/Caucasian	Employed full-time	1	Democrat